Back to leaderboard

qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx

LM-STUDIO MLX

qwen3_moe · 30B · MXFP4

Excellent

Aug 20, 2026 · Apple M4 Max

GPT-OSS-20B:20b

OLLAMA GGUF

gptoss · 20.9B · MXFP4

Excellent

Aug 18, 2026 · Intel Core™ i7-14700F

Global Score
96 vs 93
Hardware Fit
95 vs 92
Quality Score
96 vs 93

Hardware

qwen3-30b-a3b-thin… GPT-OSS-20B:20b
MachineMacBook ProHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUApple M4 MaxIntel Core™ i7-14700F
Cores1628
RAM128 GB128 GB
GPUApple M4 MaxNVIDIA GeForce RTX 5080
OSmacOS 26.5.2Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-30b-a3b-thin… GPT-OSS-20B:20b
Tokens/sec112.8178.6
First chunk21 ms695 ms
TTFT1.5 s1.4 s
Load time3.5 s31.2 s
Memory usage0.0 GB11.9 GB
Memory %0%9%

HW Fit Score Breakdown

qwen3-30b-a3b-thinking-…

Speed
50/50
TTFT
15/20
Memory
30/30

GPT-OSS-20B:20b

Speed
50/50
TTFT
12/20
Memory
30/30

Quality

qwen3-30b-a3b-thinking-…

Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

GPT-OSS-20B:20b

Reasoning
19/20
Coding
18/20
Instruction
16/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest